Comparison of single ARIMA model and ARIMA model based on seasonal decomposition for prediction of incidence rate of hepatitis C
LIU Tian1, YAO Meng-lei1, CHEN Hong-ying2, HUANG Shu-qiong2, HUANG Ji-gui1, MAO An-lu1, YANG Wen-wen2, CAI Jing2, LIU Yu-xi1
1.Jingzhou Municipal Center for Disease Control and Prevention, Jingzhou, Hubei 434000, China; 2.Hubei Provincial Center for Disease Control and Prevention, Wuhan, Hubei 430079, China
Abstract：Objective To explore the application of single autoregressive integrated moving average (ARIMA) model and ARIMA model based on seasonal decomposition to fitting and predicting the incidence rate of hepatitis C. Methods We collected the data concerning the monthly incidence rates of hepatitis C in Jingzhou City from 2007 to 2015, and then established single ARIMA model and ARIMA model based on seasonal decomposition. The monthly incidence rates of hepatitis C in 2016 were introduced back to the established models to evaluate their predictive capacity. The indexes of fitting and predicting efficiency of the two models included relative error (RE), mean relative error (MRE), mean error rate (MER), mean square error (MSE) and mean absolute error (MAE). Results The MRE, MER, MSE and MAE were 17.868, 16.367, 0.225 and 0.177 for single ARIMA fitting model; 14.090, 15.057, 0.343 and 0.284 for single ARIMA predictive model; 14.732, 13.556, 0.201 and 0.151 for ARIMA fitting model based on seasonal decomposition; and 11.778, 12.353, 0.277 and 0.229 for ARIMA predictive model based on seasonal decomposition. Conclusion ARIMA model based on seasonal decomposition is superior to single ARIMA model in fitting and predicting the incidence rate of hepatitis C.
刘天, 姚梦雷, 陈红缨, 黄淑琼, 黄继贵, 毛安禄, 杨雯雯, 蔡晶, 刘予希. 单纯ARIMA模型和基于季节性分解的ARIMA模型在丙肝发病率中的预测效果比较[J]. 实用预防医学, 2019, 26(3): 278-281.
LIU Tian, YAO Meng-lei, CHEN Hong-ying, HUANG Shu-qiong, HUANG Ji-gui, MAO An-lu, YANG Wen-wen, CAI Jing, LIU Yu-xi. Comparison of single ARIMA model and ARIMA model based on seasonal decomposition for prediction of incidence rate of hepatitis C. , 2019, 26(3): 278-281.
[1] Jacobson IM, McHutchison JG, Dusheiko G, et al. Telaprevir for previously untreated chronic hepatitis C virus infection [J]. N Engl J Med, 2011, 364(25):2405-2416. [2] WHO.factsheets.Hepatitis C[EB/OL].(2017-10-02)[2018-02-05].http://www.who.int/en/news-room/fact-sheets/detail/hepatitis-c. [3] Wang L, Xing J, Chen F, et al. Spatial analysis on hepatitis C virus infection in mainland China: from 2005 to 2011[J]. PLoS One, 2014,9(10):e110861. [4] 孙振球. 医学统计学[M] .第3版.北京:人民卫生出版社, 2010:390-404. [5] 王燕. 应用时间序列分析 [M].第2版. 北京:中国人民大学出版社, 2008:141-149. [6] 惠石生, 陈立章, 刘富强, 等. 乘积季节自回归积分滑动平均模型在流行性腮腺炎发病率预测中的应用[J]. 中华预防医学杂志, 2015,49(12):1042-1046. [7] 赵华. 时间序列数据分析:R软件应用[M]. 北京:清华大学出版社, 2016:112-120. [8] 王彤. 医学统计学与SPSS软件应用[M]. 北京:北京大学医学出版社, 2008:338-342. [9] 吴伟. 广义回归神经网络(GRNN)在肾综合征出血热发病率预测中的应用[D]. 沈阳:中国医科大学, 2008. [10] 原凌云, 周以军, 朱妮, 等.多种数据模型在手足口病发病预测的应用探讨[J].实用预防医学,2018,25(11):1400-1401. [11] 刘源, 刘富强, 陈立章, 等. 湖南省2010－2015年丙型肝炎发病流行病学特征与短期发病趋势预测[J]. 中华疾病控制杂志, 2017, 21(2):146-150. [12] Zheng YL, Zhang LP, Zhang XL, et al. Forecast model analysis for the morbidity of tuberculosis in Xinjiang, China [J]. PLoS One, 2015, 10(3):e0116832. [13] Liu L, Luan RS, Yin F, et al. Predicting the incidence of hand, foot and mouth disease in Sichuan province, China using the ARIMA model [J]. Epidemiol Infect, 2016, 144(1):144-151. [14] Zhang X, Hou F, Qiao Z, et al. Temporal and long-term trend analysis of class C notifiable diseases in China from 2009 to 2014[J]. BMJ Open, 2016,6(10):e11038. [15] Bates JM, Granger CWJ. The combination of forecasts[J]. J Oper Res Soc, 1969, 20(4):451-468. [16] 胡跃华, 廖家强, 冯国双, 等. 自回归移动平均模型在全国手足口病疫情预测中的应用[J]. 疾病监测, 2014, 29(10):827-832. [17] Wubuli A, Li Y, Xue F, et al. Seasonality of active tuberculosis notification from 2005 to 2014 in Xinjiang, China[J]. PLoS One, 2017,12(7):e180226.
2019, Vol. 26 
